© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90337
    Prev
    Next
    INDEX
    Explanations

    participating in diverse entities

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on occurrences of the word “participating” (often in contexts listing participants or participant counts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     The
    -2.16
     perfekte
    -2.08
     Aunque
    -2.03
     koruyucu
    -2.02
     tuvo
    -2.00
     helse
    -2.00
     bazen
    -1.99
     katkıda
    -1.99
    Sqft
    -1.98
    过于
    -1.97
    POSITIVE LOGITS
    ୌ
    2.61
     participating
    2.48
    at
    2.25
    玙
    2.25
     Houſe
    2.20
     collaborating
    2.19
     shows
    2.19
    a
    2.14
    नलोड
    2.13
     cooperating
    2.11
    Activations Density 0.019%

    No Known Activations